Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     κατά
    -0.07
     واک
    -0.07
    -0.07
     diplomatic
    -0.07
     accl
    -0.07
     dispatch
    -0.07
     (,
    -0.07
     ___
    -0.07
     climat
    -0.07
     incision
    -0.07
    POSITIVE LOGITS
    我要
    0.09
    机制
    0.08
     Preliminary
    0.08
     Minimal
    0.08
     Machine
    0.07
    机
    0.07
    -machine
    0.07
     содержание
    0.07
    �
    0.07
     Chardonnay
    0.07
    Act Density 0.041%

    No Known Activations